Answers are grounded in this paper and cite their sources.
This focused scoping review examines the development, current applications, and future translational opportunities of artificial intelligence (AI) in minimally invasive surgery (MIS) and robotic-assisted procedures. A literature search was carried out across PubMed, IEEE Xplore, and Google Scholar to evaluate artificial intelligence applications for intraoperative surgical guidance in minimally invasive and robotic procedures. Eligible publications were analyzed across technical architectures, clinical data modalities, evaluation metrics, and translational constraints to characterize the continuum from early manual laparoscopy to modern algorithmic assistance. Current literature demonstrates a steady transition toward multimodal deep learning architectures, including convolutional neural networks, vision transformers, and recurrent sequence models. Modern platforms achieve high accuracy under controlled conditions in instrument tracking, procedural phase recognition, and anatomical landmark identification. In preclinical settings, supervised task-autonomous systems-such as the Smart Tissue Autonomous Robot-have demonstrated higher consistency in automated suturing metrics relative to manual techniques. However, translation into real-world operating rooms remains constrained by dataset homogeneity, annotation bottlenecks, intraoperative visual disruptions (e.g., surgical smoke and blood fouling), processing latency, and algorithmic opacity. Concurrently, evolving medicolegal and informed-consent frameworks raise unresolved questions regarding institutional accountability and surgeon responsibility when predictive systems fail. Successful clinical translation will likely depend on decentralized federated learning networks, real-time image restoration, structured institutional credentialing, and supervised shared-control systems that assist with standardized procedural steps while keeping clinicians firmly in the decision-making loop.
No takes yet. Share an insight, caveat, or question.
REMY MILLER (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: